scan, split, OCR, prepare for LLM
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Evgeniy Ierusalimov 57152efb4b updated discovered self skills 1 mese fa
..
AGENTS.md initial release with base split functionality 2 mesi fa
AI_RULES.md refactored code 2 mesi fa
ARCHITECTURE.md renamed inage_split to image_prepare, fixed some code and parameters 2 mesi fa
CODE_STYLE.md polishing the code and docs 2 mesi fa
DEVELOPMENT.md refactored code 2 mesi fa
IMAGE_PROCESSING.md refactored code 2 mesi fa
README.md initial release with base split functionality 2 mesi fa
REQUIREMENTS.md initial release with base split functionality 2 mesi fa
SKILLS.md updated discovered self skills 1 mese fa
SOLID_AUDIT.md polishing the code and docs 2 mesi fa
TASKS.md initial release with base split functionality 2 mesi fa
VLM_OFFLOAD.md polishing the code and docs 2 mesi fa

README.md

Offline Document Pipeline

Назначение проекта

Преобразование больших технических документов, полученных после печати и сканирования, в структурированный HTML без использования облачных сервисов.

Поддерживается полностью offline работа.

Pipeline

JPEG/TIFF/PDF

↓

Split pages

↓

Deskew

↓

Crop

↓

PaddleOCR

↓

HTML

Вне scope проекта

  • LLM
  • RAG
  • поиск
  • анализ документов